Artificial intelligence news.
Straight from the original announcements.

B200

OpenRouter calculates when self-hosting an LLM beats API costs
For developersNovember 12, 2026

OpenRouter calculates when self-hosting an LLM beats API costs

Self-hosting an open-weight LLM costs less than using an API only when traffic keeps the GPU busy enough, according to an OpenRouter analysis. Its calculations show that…

Ai2 replaces priority scheduler with GPU time budgets to fund high-impact research
Chips and infrastructureOctober 9, 2026, 10:00

Ai2 replaces priority scheduler with GPU time budgets to fund high-impact research

Ai2 has replaced the priority-based scheduler on its GPU clusters with a system built on GPU time budgets, hierarchical fair-share allocation and a time-slicing…

For developers
For developersOctober 7, 2026, 00:57

PyTorch's FBTriton Kernels for Table Batched Embeddings Beat Legacy CUDA

PyTorch has published a technical walkthrough of FBTriton, a Triton-based implementation of the Table Batched Embedding (TBE) forward and backward kernels used in…

Baseten's AI-built inference engine beats vLLM by up to 90% on Qwen decode
For developersOctober 2, 2026, 23:09

Baseten's AI-built inference engine beats vLLM by up to 90% on Qwen decode

Baseten says an inference engine generated by an AI agent outperformed vLLM 0.25.1 by up to 90% on single-stream decode speed for Qwen-3.6-35B-A3B in NVFP4 precision on…